matt-grilling
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user plans and environment facts to generate its analysis.
- Ingestion points: Processes untrusted input from the user (plans, decisions, ideas) and facts retrieved from the environment (filesystem, tools) as mentioned in SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate external data from the skill's operational instructions.
- Capability inventory: The skill is instructed to access the filesystem, use tools like
tw brief, and dispatch sub-agents to find information. - Sanitization: No methods for sanitizing, escaping, or validating ingested data are specified before processing.
Audit Metadata